Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World

TL;DR

This paper introduces Trans4Trans, an efficient Transformer-based model designed for real-time segmentation of transparent objects to aid visually impaired individuals in navigation, demonstrating superior performance and practical usability.

Contribution

The paper presents a novel dual-head Transformer model with a Transformer Parsing Module for joint learning, optimized for transparent object segmentation in assistive navigation systems.

Findings

Outperforms state-of-the-art on Stanford2D3D and Trans10K-v2 datasets

Achieves high mIoU scores of 45.13% and 75.14%

Validated through user studies in real-world scenarios

Abstract

Common fully glazed facades and transparent objects present architectural barriers and impede the mobility of people with low vision or blindness, for instance, a path detected behind a glass door is inaccessible unless it is correctly perceived and reacted. However, segmenting these safety-critical objects is rarely covered by conventional assistive technologies. To tackle this issue, we construct a wearable system with a novel dual-head Transformer for Transparency (Trans4Trans) model, which is capable of segmenting general and transparent objects and performing real-time wayfinding to assist people walking alone more safely. Especially, both decoders created by our proposed Transformer Parsing Module (TPM) enable effective joint learning from different datasets. Besides, the efficient Trans4Trans model composed of symmetric transformer-based encoder and decoder, requires little computational expenses and is readily deployed on portable GPUs. Our Trans4Trans model outperforms state-of-the-art methods on the test sets of Stanford2D3D and Trans10K-v2 datasets and obtains mIoU of 45.13% and 75.14%, respectively. Through various pre-tests and a user study conducted in indoor and outdoor scenarios, the usability and reliability of our assistive system have been extensively verified.